Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 88165
    Prev
    Next
    INDEX
    Explanations

    found

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    を集め
    -0.08
     bụ
    -0.08
    /u
    -0.07
    大きく
    -0.07
    eg
    -0.07
    column
    -0.07
    �
    -0.07
     GI
    -0.07
    hr
    -0.07
    -sc
    -0.07
    POSITIVE LOGITS
     SOUR
    0.07
     Formal
    0.07
    增强了
    0.06
     Activate
    0.06
    밨
    0.06
     SPI
    0.06
    -coded
    0.06
    瞎
    0.06
     tgt
    0.06
     pointers
    0.06
    Activations Density 0.000%

    No Known Activations